INDEX

Explanations

occurrences of addresses within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸ĩà¸²à¸Ļ

-0.16

repid

-0.16

ties

-0.15

cken

-0.15

Ø²Ø§Ø±

-0.14

idor

-0.14

ì¦Ī

-0.14

/fixtures

-0.14

ayo

-0.14

tings

-0.14

POSITIVE LOGITS

(es

0.25

istrovstvÃŃ

0.22

ses

0.21

Î¸ÎµÎ½

0.15

sed

0.15

nowled

0.15

alette

0.15

eses

0.15

oused

0.14

alarda

0.14

Activations Density 0.022%

occurrences of addresses within the text

No Comments

No Known Activations